Deep learning-based left heart chambers segmentation and strain analysis from dynamic MRI images - Institut de Recherche sur les Maladies Cardiovasculaires, du Métabolisme et de la Nutrition
Communication Dans Un Congrès Année : 2024

Deep learning-based left heart chambers segmentation and strain analysis from dynamic MRI images

Perrine Marsac
  • Fonction : Auteur
  • PersonId : 1382072
  • IdRef : 277510937
Elie Mousseaux
Gilles Montalescot

Résumé

Feature tracking (FT) is increasingly used on dynamic magnetic resonance images for myocardial strain evaluation, but often requires manual initialization of heart chambers, which is tedious and source of variability, especially on the challenging long axis images. Accordingly, we combined a deep learning (DL) approach with FT (DL-FT) to provide fully automated time-resolved left ventricular (LV) and atrial (LA) delineation and strain analysis. This approach was tested on a multi-center and multi-vendor database of 684 healthy controls and patients. DL-initialization achieved Dice scores of 0.89±0.11 for LV endocardium, 0.93±0.07 for LV epicardium and 0.89±0.10 for LA on the testing set of 108 datasets (2-and 4-chambers). LA and LV DL-FT strain peaks were highly associated with expert strains as revealed by correlation coefficients=0.96 for LV and ≥0.70 for LA and mean Bland-Altman biases=0.62% for LV and <1% for LA. Results also revealed stability of our approach over vendors and field strengths.

Fichier principal
Vignette du fichier
881.pdf (250.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04677983 , version 1 (26-08-2024)

Identifiants

Citer

Jonas Leite, Moussa Gueda, Emilie Bollache, Khaoula Bouazizi, Perrine Marsac, et al.. Deep learning-based left heart chambers segmentation and strain analysis from dynamic MRI images. 2024 IEEE International Symposium on Biomedical Imaging (ISBI), May 2024, Athènes, Greece. pp.1-4, ⟨10.1109/ISBI56570.2024.10635336⟩. ⟨hal-04677983⟩
81 Consultations
15 Téléchargements

Altmetric

Partager

More